From a78db10941d0818b0077d1fb6d1795d9ebb34f99 Mon Sep 17 00:00:00 2001 From: Akhilesh Date: Tue, 12 Feb 2019 22:58:39 +0530 Subject: [PATCH] add kannada support (#3264) * add kannada support * add few more stop words * add support for Kannada Language --- .github/contributors/akki2825.md | 87 ++++++++++++++++++++++++++++++++ spacy/lang/kn/__init__.py | 21 ++++++++ spacy/lang/kn/stop_words.py | 69 +++++++++++++++++++++++++ 3 files changed, 177 insertions(+) create mode 100644 .github/contributors/akki2825.md create mode 100644 spacy/lang/kn/__init__.py create mode 100644 spacy/lang/kn/stop_words.py diff --git a/.github/contributors/akki2825.md b/.github/contributors/akki2825.md new file mode 100644 index 000000000..bc4cda0cb --- /dev/null +++ b/.github/contributors/akki2825.md @@ -0,0 +1,87 @@ +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | -------------------- | +| Name | Akhilesh K R | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2019-02-12 | +| GitHub username | akki2825 | +| Website (optional) | | diff --git a/spacy/lang/kn/__init__.py b/spacy/lang/kn/__init__.py new file mode 100644 index 000000000..3eb7fba3a --- /dev/null +++ b/spacy/lang/kn/__init__.py @@ -0,0 +1,21 @@ +# coding: utf8 +from __future__ import unicode_literals + +from .stop_words import STOP_WORDS +from .lex_attrs import LEX_ATTRS + +from ..norm_exceptions import BASE_NORMS +from ...language import Language +from ...attrs import LANG + + +class KannadaDefaults(Language.Defaults): + stop_words = STOP_WORDS + + +class Kannada(Language): + lang = 'kn' + Defaults = KannadaDefaults + + +__all__ = ['Kannada'] diff --git a/spacy/lang/kn/stop_words.py b/spacy/lang/kn/stop_words.py new file mode 100644 index 000000000..38f79c148 --- /dev/null +++ b/spacy/lang/kn/stop_words.py @@ -0,0 +1,69 @@ +# coding: utf8 +from __future__ import unicode_literals + +# Stop words + +STOP_WORD = set(""" +ಈ +ಮತ್ತು +ಹಾಗೂ +ಅವರು +ಅವರ +ಬಗ್ಗೆ +ಎಂಬ +ಆದರೆ +ಅವರನ್ನು +ಆದರೆ +ತಮ್ಮ +ಒಂದು +ಎಂದರು +ಮೇಲೆ +ಹೇಳಿದರು +ಸೇರಿದಂತೆ +ಬಳಿಕ +ಆ +ಯಾವುದೇ +ಅವರಿಗೆ +ನಡೆದ +ಕುರಿತು +ಇದು +ಅವರು +ಕಳೆದ +ಇದೇ +ತಿಳಿಸಿದರು +ಹೀಗಾಗಿ +ಕೂಡ +ತನ್ನ +ತಿಳಿಸಿದ್ದಾರೆ +ನಾನು +ಹೇಳಿದ್ದಾರೆ +ಈಗ +ಎಲ್ಲ +ನನ್ನ +ನಮ್ಮ +ಈಗಾಗಲೇ +ಇದಕ್ಕೆ +ಹಲವು +ಇದೆ +ಮತ್ತೆ +ಮಾಡುವ +ನೀಡಿದರು +ನಾವು +ನೀಡಿದ +ಇದರಿಂದ +ಅದು +ಇದನ್ನು +ನೀಡಿದ್ದಾರೆ +ಅದನ್ನು +ಇಲ್ಲಿ +ಆಗ +ಬಂದಿದೆ. +ಅದೇ +ಇರುವ +ಅಲ್ಲದೆ +ಕೆಲವು +ನೀಡಿದೆ +ಇದರ +ಇನ್ನು +ನಡೆದಿದೆ +""".split())